Abstract
As the economy continues to grow, more and more people tend to increase their income through asset investment. This paper devised a trading strategy and evaluated the value of an investment of $1,000 after five years. The Catboost regression model was built to predict the price of gold and bitcoin with an accuracy rate of up to 99%. It showed that the model can effectively make predictions about gold and bitcoin prices. Trading signals for gold and bitcoin were established based on the Bollinger Bands channel theory. Simulated trading of assets began on September 11, 2016, and the total assets after five years were $4,430,859.83. Then this paper conducted sensitivity analysis on the established trading model. Finally, the parameters of the established trading model are optimized to determine an optimal model parameter.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
